Using Rank Propagation and Probabilistic Counting for Link-based Spam Detection

author: Carlos Castillo, Yahoo! Research, Yahoo!

Categories

Top: Computer Science: Network Analysis
Top: Computer Science: Web Mining

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Using Rank Propagation and Probabilistic Counting for Link-based Spam Dete
0:26	Content
0:54	What is on the Web?
1:32	Web spam (keywords + links)
2:20	Web spam (mostly keywords)
2:44	Search engine?
3:14	Fake search engine
3:24	Problem: “normal” pages that are spam
3:56	Link farms
5:23	Motivation
6:01	Metrics
7:18	Test collection
8:11	Degree-based measures
8:16	Degree
9:01	Degree
9:14	Edge reciprocity
10:09	Assortativity
11:08	Automatic classifier
12:48	PageRank
12:50	PageRank
13:00	Maximum PageRank in the Host
13:25	Variance of PageRank
14:15	Variance of PageRank of in-neighbors
14:39	Automatic classifier
15:09	TrustRank
15:18	TrustRank
16:05	TrustRank score
16:55	TrustRank / PageRank
17:13	Automatic classifier
17:36	Truncated PageRank
17:42	Path-based formula for PageRank
18:11	General functional ranking
18:49	Truncated PageRank
19:48	Truncated PageRank(T=2) / PageRank
20:14	Max. change of Truncated PageRank
20:31	Automatic classifier
20:51	Counting supporters
20:55	Idea: count “supporters” at different distances
21:37	High and low-ranked pages are different
22:09	Probabilistic count
22:50	Hosts at distance 4
23:07	Automatic classifier
23:16	Conclusions
23:21	Summary of classifiers
25:07	Top 10 metrics
25:12	Conclusions

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.